lang-word-tokenizers / data /Cariban.json
guipenedo's picture
guipenedo HF staff
do not propagate to the root
49dc1e7 unverified
{
"name": "Cariban",
"depth": 0,
"iso_1_code": null,
"iso_3_code": null,
"children": [
{
"name": "Carib",
"depth": 1,
"iso_1_code": null,
"iso_3_code": "car",
"children": [],
"family": "Cariban",
"tokenizers": {},
"node_i": "3308",
"native_tokenizers": [],
"scripts": [
"Latn"
]
},
{
"name": "Central",
"depth": 1,
"iso_1_code": null,
"iso_3_code": null,
"children": [
{
"name": "Apala\u00ed",
"depth": 2,
"iso_1_code": null,
"iso_3_code": "apy",
"children": [],
"family": "Cariban",
"tokenizers": {},
"node_i": "3310",
"native_tokenizers": [],
"scripts": [
"Latn"
]
},
{
"name": "Cuman\u00e1",
"depth": 2,
"iso_1_code": null,
"iso_3_code": null,
"children": [
{
"name": "Chaima",
"depth": 3,
"iso_1_code": null,
"iso_3_code": "ciy",
"children": [],
"family": "Cariban",
"tokenizers": {},
"node_i": "3312",
"native_tokenizers": [],
"scripts": []
},
{
"name": "Cumanagoto",
"depth": 3,
"iso_1_code": null,
"iso_3_code": "cuo",
"children": [],
"family": "Cariban",
"tokenizers": {},
"node_i": "3313",
"native_tokenizers": [],
"scripts": []
}
],
"family": "Cariban",
"tokenizers": {},
"node_i": "3311",
"native_tokenizers": [],
"scripts": []
},
{
"name": "Makiritare",
"depth": 2,
"iso_1_code": null,
"iso_3_code": null,
"children": [
{
"name": "Maquiritari",
"depth": 3,
"iso_1_code": null,
"iso_3_code": "mch",
"children": [],
"family": "Cariban",
"tokenizers": {},
"node_i": "3315",
"native_tokenizers": [],
"scripts": []
}
],
"family": "Cariban",
"tokenizers": {},
"node_i": "3314",
"native_tokenizers": [],
"scripts": []
},
{
"name": "Mapoyo-Yavarana",
"depth": 2,
"iso_1_code": null,
"iso_3_code": null,
"children": [
{
"name": "Mapoyo",
"depth": 3,
"iso_1_code": null,
"iso_3_code": "mcg",
"children": [],
"family": "Cariban",
"tokenizers": {},
"node_i": "3317",
"native_tokenizers": [],
"scripts": []
},
{
"name": "P\u00e9mono",
"depth": 3,
"iso_1_code": null,
"iso_3_code": "pev",
"children": [],
"family": "Cariban",
"tokenizers": {},
"node_i": "3318",
"native_tokenizers": [],
"scripts": []
},
{
"name": "Tamanaku",
"depth": 3,
"iso_1_code": null,
"iso_3_code": "tmz",
"children": [],
"family": "Cariban",
"tokenizers": {},
"node_i": "3319",
"native_tokenizers": [],
"scripts": []
},
{
"name": "Yabarana",
"depth": 3,
"iso_1_code": null,
"iso_3_code": "yar",
"children": [],
"family": "Cariban",
"tokenizers": {},
"node_i": "3320",
"native_tokenizers": [],
"scripts": []
}
],
"family": "Cariban",
"tokenizers": {},
"node_i": "3316",
"native_tokenizers": [],
"scripts": []
},
{
"name": "Wayana",
"depth": 2,
"iso_1_code": null,
"iso_3_code": null,
"children": [
{
"name": "Kaxui\u00e2na",
"depth": 3,
"iso_1_code": null,
"iso_3_code": "kbb",
"children": [],
"family": "Cariban",
"tokenizers": {},
"node_i": "3322",
"native_tokenizers": [],
"scripts": []
},
{
"name": "Wayana",
"depth": 3,
"iso_1_code": null,
"iso_3_code": "way",
"children": [],
"family": "Cariban",
"tokenizers": {},
"node_i": "3323",
"native_tokenizers": [],
"scripts": [
"Latn"
]
}
],
"family": "Cariban",
"tokenizers": {},
"node_i": "3321",
"native_tokenizers": [],
"scripts": []
}
],
"family": "Cariban",
"tokenizers": {},
"node_i": "3309",
"native_tokenizers": [],
"scripts": []
},
{
"name": "Kashuyana",
"depth": 1,
"iso_1_code": null,
"iso_3_code": null,
"children": [
{
"name": "Sikiana",
"depth": 2,
"iso_1_code": null,
"iso_3_code": "sik",
"children": [],
"family": "Cariban",
"tokenizers": {},
"node_i": "3325",
"native_tokenizers": [],
"scripts": []
}
],
"family": "Cariban",
"tokenizers": {},
"node_i": "3324",
"native_tokenizers": [],
"scripts": []
},
{
"name": "North Amazonian",
"depth": 1,
"iso_1_code": null,
"iso_3_code": null,
"children": [
{
"name": "Pem\u00f3n",
"depth": 2,
"iso_1_code": null,
"iso_3_code": null,
"children": [
{
"name": "Pem\u00f3n proper",
"depth": 3,
"iso_1_code": null,
"iso_3_code": null,
"children": [
{
"name": "Pemon",
"depth": 4,
"iso_1_code": null,
"iso_3_code": "aoc",
"children": [],
"family": "Cariban",
"tokenizers": {},
"node_i": "3329",
"native_tokenizers": [],
"scripts": []
},
{
"name": "Macushi",
"depth": 4,
"iso_1_code": null,
"iso_3_code": "mbc",
"children": [],
"family": "Cariban",
"tokenizers": {},
"node_i": "3330",
"native_tokenizers": [],
"scripts": [
"Latn"
]
},
{
"name": "Kapong",
"depth": 4,
"iso_1_code": null,
"iso_3_code": null,
"children": [
{
"name": "Akawaio",
"depth": 5,
"iso_1_code": null,
"iso_3_code": "ake",
"children": [],
"family": "Cariban",
"tokenizers": {},
"node_i": "3332",
"native_tokenizers": [],
"scripts": [
"Latn"
]
},
{
"name": "Patamona",
"depth": 5,
"iso_1_code": null,
"iso_3_code": "pbc",
"children": [],
"family": "Cariban",
"tokenizers": {},
"node_i": "3333",
"native_tokenizers": [],
"scripts": [
"Latn"
]
}
],
"family": "Cariban",
"tokenizers": {},
"node_i": "3331",
"native_tokenizers": [],
"scripts": []
}
],
"family": "Cariban",
"tokenizers": {},
"node_i": "3328",
"native_tokenizers": [],
"scripts": []
}
],
"family": "Cariban",
"tokenizers": {},
"node_i": "3327",
"native_tokenizers": [],
"scripts": []
},
{
"name": "Yawaper\u00ed",
"depth": 2,
"iso_1_code": null,
"iso_3_code": null,
"children": [
{
"name": "Waimiri-Atroar\u00ed",
"depth": 3,
"iso_1_code": null,
"iso_3_code": "atr",
"children": [],
"family": "Cariban",
"tokenizers": {},
"node_i": "3335",
"native_tokenizers": [],
"scripts": []
}
],
"family": "Cariban",
"tokenizers": {},
"node_i": "3334",
"native_tokenizers": [],
"scripts": []
}
],
"family": "Cariban",
"tokenizers": {},
"node_i": "3326",
"native_tokenizers": [],
"scripts": []
},
{
"name": "South Amazonian",
"depth": 1,
"iso_1_code": null,
"iso_3_code": null,
"children": [
{
"name": "E\u2019\u00f1apa Woromaipu",
"depth": 2,
"iso_1_code": null,
"iso_3_code": "pbh",
"children": [],
"family": "Cariban",
"tokenizers": {},
"node_i": "3337",
"native_tokenizers": [],
"scripts": []
},
{
"name": "Arara",
"depth": 2,
"iso_1_code": null,
"iso_3_code": null,
"children": [
{
"name": "Arara, Par\u00e1",
"depth": 3,
"iso_1_code": null,
"iso_3_code": "aap",
"children": [],
"family": "Cariban",
"tokenizers": {},
"node_i": "3339",
"native_tokenizers": [],
"scripts": []
},
{
"name": "Ikpeng",
"depth": 3,
"iso_1_code": null,
"iso_3_code": "txi",
"children": [],
"family": "Cariban",
"tokenizers": {},
"node_i": "3340",
"native_tokenizers": [],
"scripts": []
}
],
"family": "Cariban",
"tokenizers": {},
"node_i": "3338",
"native_tokenizers": [],
"scripts": []
},
{
"name": "Bakair\u00ed",
"depth": 2,
"iso_1_code": null,
"iso_3_code": null,
"children": [
{
"name": "Bakair\u00ed",
"depth": 3,
"iso_1_code": null,
"iso_3_code": "bkq",
"children": [],
"family": "Cariban",
"tokenizers": {},
"node_i": "3342",
"native_tokenizers": [],
"scripts": [
"Latn"
]
},
{
"name": "Amonap",
"depth": 3,
"iso_1_code": null,
"iso_3_code": null,
"children": [
{
"name": "Kuik\u00faro-Kalap\u00e1lo",
"depth": 4,
"iso_1_code": null,
"iso_3_code": "kui",
"children": [],
"family": "Cariban",
"tokenizers": {},
"node_i": "3344",
"native_tokenizers": [],
"scripts": []
},
{
"name": "Matipuhy",
"depth": 4,
"iso_1_code": null,
"iso_3_code": "mzo",
"children": [],
"family": "Cariban",
"tokenizers": {},
"node_i": "3345",
"native_tokenizers": [],
"scripts": []
}
],
"family": "Cariban",
"tokenizers": {},
"node_i": "3343",
"native_tokenizers": [],
"scripts": []
}
],
"family": "Cariban",
"tokenizers": {},
"node_i": "3341",
"native_tokenizers": [],
"scripts": []
}
],
"family": "Cariban",
"tokenizers": {},
"node_i": "3336",
"native_tokenizers": [],
"scripts": []
},
{
"name": "Tiriy\u00f3",
"depth": 1,
"iso_1_code": null,
"iso_3_code": null,
"children": [
{
"name": "Salum\u00e1",
"depth": 2,
"iso_1_code": null,
"iso_3_code": "slj",
"children": [],
"family": "Cariban",
"tokenizers": {},
"node_i": "3347",
"native_tokenizers": [],
"scripts": []
},
{
"name": "Karihona",
"depth": 2,
"iso_1_code": null,
"iso_3_code": null,
"children": [
{
"name": "Carijona",
"depth": 3,
"iso_1_code": null,
"iso_3_code": "cbd",
"children": [],
"family": "Cariban",
"tokenizers": {},
"node_i": "3349",
"native_tokenizers": [],
"scripts": []
}
],
"family": "Cariban",
"tokenizers": {},
"node_i": "3348",
"native_tokenizers": [],
"scripts": []
},
{
"name": "Tiriy\u00f3",
"depth": 2,
"iso_1_code": null,
"iso_3_code": null,
"children": [
{
"name": "Akurio",
"depth": 3,
"iso_1_code": null,
"iso_3_code": "ako",
"children": [],
"family": "Cariban",
"tokenizers": {},
"node_i": "3351",
"native_tokenizers": [],
"scripts": []
},
{
"name": "Tri\u00f3",
"depth": 3,
"iso_1_code": null,
"iso_3_code": "tri",
"children": [],
"family": "Cariban",
"tokenizers": {},
"node_i": "3352",
"native_tokenizers": [],
"scripts": []
}
],
"family": "Cariban",
"tokenizers": {},
"node_i": "3350",
"native_tokenizers": [],
"scripts": []
}
],
"family": "Cariban",
"tokenizers": {},
"node_i": "3346",
"native_tokenizers": [],
"scripts": []
},
{
"name": "Waiwai",
"depth": 1,
"iso_1_code": null,
"iso_3_code": null,
"children": [
{
"name": "Hixkary\u00e1na",
"depth": 2,
"iso_1_code": null,
"iso_3_code": "hix",
"children": [],
"family": "Cariban",
"tokenizers": {},
"node_i": "3354",
"native_tokenizers": [],
"scripts": [
"Latn"
]
},
{
"name": "Waiwai",
"depth": 2,
"iso_1_code": null,
"iso_3_code": "waw",
"children": [],
"family": "Cariban",
"tokenizers": {},
"node_i": "3355",
"native_tokenizers": [],
"scripts": []
}
],
"family": "Cariban",
"tokenizers": {},
"node_i": "3353",
"native_tokenizers": [],
"scripts": []
},
{
"name": "Yukpa",
"depth": 1,
"iso_1_code": null,
"iso_3_code": null,
"children": [
{
"name": "Yucpa-Yapreria",
"depth": 2,
"iso_1_code": null,
"iso_3_code": null,
"children": [
{
"name": "Japreria",
"depth": 3,
"iso_1_code": null,
"iso_3_code": "jru",
"children": [],
"family": "Cariban",
"tokenizers": {},
"node_i": "3358",
"native_tokenizers": [],
"scripts": []
},
{
"name": "Yukpa",
"depth": 3,
"iso_1_code": null,
"iso_3_code": "yup",
"children": [],
"family": "Cariban",
"tokenizers": {},
"node_i": "3359",
"native_tokenizers": [],
"scripts": [
"Latn"
]
}
],
"family": "Cariban",
"tokenizers": {},
"node_i": "3357",
"native_tokenizers": [],
"scripts": []
}
],
"family": "Cariban",
"tokenizers": {},
"node_i": "3356",
"native_tokenizers": [],
"scripts": []
}
],
"family": "Cariban",
"tokenizers": {},
"node_i": "3307",
"native_tokenizers": [],
"scripts": []
}